KR20140139466A

KR20140139466A - automatic sales forecasting system based on data crawling and manager's input

Info

Publication number: KR20140139466A
Application number: KR20140157122A
Authority: KR
Inventors: 변동삼; 이영수; 김하나한
Original assignee: 변동삼
Priority date: 2014-11-12
Filing date: 2014-11-12
Publication date: 2014-12-05

Abstract

In forecasting sales, the present invention relates to a method for predicting sales forecasts of news items such as sales related news, weather, sports, search trends, holidays, anniversaries, audience ratings, economic indicators, statistical data, SNS, The comment data is crawled and used as additional attribute data for prediction, generation of a dataset through preprocessing, generation of a prediction model by a predetermined algorithm, and calculation of a sales forecast value corresponding to a prediction target date, To provide sales forecasting information, and to improve the dataset and forecasting model by inputting values for factors that affect sales such as feedback on forecast results and events, promotions, events and uniqueness. It improves prediction accuracy by feature.

Description

[0001] AUTOMATIC SALES FORECASTING SYSTEM BASED ON DATA CRAWLING AND MANAGER'S INPUT BASED ON DATA COULDING AND MANAGER INPUTS [

The present invention relates to a device for predicting future sales volume based on crawling data affecting sales and data input by an administrator.

It is difficult to collect, search, analyze, and store data that is rapidly increasing through various media such as the Internet, smartphone, and SNS distribution. As a new paradigm of the IT industry, Has emerged as a major technology.

Large data generated from various media is difficult to collect, search, analyze, and store by conventional data processing methods. Big data technology is gradually being developed to process and utilize such large amount of data. Big data can be expressed in terms of volume, variety, and velocity. Volume refers to a larger size than existing data, and Variety includes a variety of data beyond common data. Velocity is the data that is generated every day and its creation and processing speed. As such, efforts are being made to utilize such big data as a policy not only for companies but also for national interests to create profits and strengthen national competitiveness. As a background of the present invention, there is a case in which sales data and past stock amount are predicted by using statistical analysis, and there is a prediction method by time series and artificial intelligence analysis.

One embodiment of the present invention is to provide a device for predicting future sales volume based on data crawling that affects sales and data input by an administrator.

As a technical means for achieving the above-mentioned object, an apparatus for predicting sales of the present invention includes a data crawling engine unit for crawling past and real-time data on the web, which may be attributes for prediction; A database unit for storing and managing sales statistic data from past to present and the crawled attribute data; A data set generation unit for generating a data set including a training set and a test set for prediction, the data set including a data preprocessing step for data of the database unit; A data mining engine unit for calculating a sales forecast value corresponding to a forecast target date based on the data set through selection and predetermined prediction models and algorithms; A sales forecast information providing unit for providing the sales forecast value to the manager; An attribute data manual input unit for inputting data predicted by the manager to affect a sales forecast and using the data as attribute data for prediction to improve the accuracy of the prediction; .

The present invention crawls news, weather, sports, search trends, holidays, anniversaries, ratings, economic indicators, statistical data, SNS, bulletin board posts, and comment data compared to existing simple statistical and artificial intelligence analysis prediction methods In addition, by using the store manager's feedback on the prediction result and the know-how attribute value for inputting the manual, it is possible to increase the efficiency of ordering inventory and quantity by increasing the prediction accuracy, .

1 is a block diagram illustrating the elements and data flow of an automated sales forecasting system based on data crawling and manager input according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and like parts are denoted by similar reference numerals throughout the specification.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise.

1 is a block diagram showing a configuration of an automatic sales forecasting apparatus based on data crawling and manager input according to an embodiment of the present invention.

As shown in Fig. The apparatus 110 for predicting sales according to an embodiment of the present invention includes a data crawling engine unit 120 for crawling past and real time data 131 on the web 10 that can be attributes for prediction, A database 130 for storing and managing the sales statistics data 132 and the crawled attribute data 131 and a data preprocessing process 142 for data of the database 130, A data set generation unit 140 for generating a data set 143 including a test set and a sales forecast value corresponding to the forecasted target day based on the data set 143 through a predetermined and predetermined prediction model and algorithm A sales forecasting unit 151 for providing the sales forecast value 151 to the manager 100, an information providing unit 160 for managing the sales forecast value 151 to the manager 100, Data 171, which is predicted to affect The force by using the attribute data for prediction 151 is configured to include attribute data manual input unit 170 to improve the accuracy of prediction (151).

The data crawling engine unit 120 crawls past and current news related to the sales industry, weather, sports, search trends, holidays, anniversaries, ratings, economic indicators, statistical data, SNS, bulletin board posts, comment data, And inquires whether there is new data in the web page 10 in which the data 131 exists at every period of time and crawls.

The database unit 130 stores the sales statistics data 132 and the crawl data 132 including the number of orders and the number of orders and the amount of goods, the goods, the customer information, the providing method, the discount, 131).

The data set generating unit 140 may include an opinion mining process 141 for analyzing affirmative and negative factors for a sales product related issue, a seller, and a competitor through natural language processing in news, SNS, And a data preprocessing process 142 for performing a major influential property selection and data dimension extraction, including refinement, integration, and change of the data 130 and the data 130, and generates a data set 143 for prediction .

The data mining engine unit 150 includes algorithms such as time series, artificial neural network, decision tree, rule, and linear regression analysis, and combines the respective algorithms through the techniques of bagging, boosting, and boat to generate a prediction model Generates and generates a sales forecast value 151, and updates the predictive model by repeating learning of the latest data set 143 at a predetermined period.

The sales forecast information providing unit 160 displays and visualizes the sales forecast values 151 in various sections and forms in the form of a table, a graph, a numerical value, etc. through an interface 165 such as a program, a web, and an application.

The attribute data manual input unit 170 is a unit for manually inputting the attribute 171 affecting sales such as feedback, event, promotion, surrounding event, uniqueness, etc. on the sales forecast value 151 through the interface 165 To directly enhance the data set 143 and prediction model.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

One embodiment of the present invention may also be embodied in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include both computer storage media and communication media. Computer storage media is computer readable

Volatile, removable and non-removable media implemented in any method or technology for storage of information such as instructions, data structures, program modules or other data. Communication media typically includes any information delivery media, including computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism.

Furthermore, while the methods and systems of the present invention have been described in terms of specific embodiments, some or all of those elements or operations may be implemented using a computer system having a general purpose hardware architecture.

It is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. .

10: WEB
100: Store Manager
110: Automated sales forecasting based on data crawling and manager input
120: Data crawling engine
130:
131: External crawl property data
132: Sales Statistics Data
140:
141: Opinion Mining Course
142: Data preprocessing process
143: Data set including training set, test set
150: Data mining engine section
151: Sales forecast result value corresponding to the forecast target date
160: Sales forecast information offerer
165: Manager interface
170: Attribute data manual input unit
171: Administrator Manual Entry Additional Attribute Data

Claims

1. An apparatus for predicting sales,
A data crawling engine unit for crawling past and real-time data on the web that can be attributes for prediction;
A database unit for storing and managing sales statistic data from past to present and the crawled attribute data;
A data set generation unit for generating a data set including a training set and a test set for prediction, the data set including a data preprocessing process for data of the database unit;
A data mining engine unit for calculating a sales forecast value corresponding to a forecast target date based on the data set through selection and predetermined prediction models and algorithms;
A sales forecast information providing unit for providing the sales forecast value to the manager;
An attribute data manual input unit for inputting data predicted by the manager to affect a sales forecast and using the data as attribute data for prediction to improve the accuracy of the prediction; And a sales forecasting automation device based on the data crawling and manager input.

The method according to claim 1,
The data crawling engine unit,
The above data is crawled at every predetermined period of time by crawling past and present news related to the sales industry, weather, sports, search trend, holiday, anniversary, audience rating, economic index, statistical data, SNS, Wherein the web page is crawled by inquiring whether there is new data in the web page.

The method according to claim 1,
The database unit,
And stores and manages the sales statistics data and the crawl data that are accumulated continuously including the number of orders and the number of orders, amount, amount of goods, customer information, providing method, discount, specificity, Automated sales forecasting based on data crawling and manager input.

The method according to claim 1,
The data-
Among the above data, Opinion Mining process of analyzing affirmative and negative factors for sales product related issues, sellers and competitors through natural language processing in news, SNS, and posting, and the refining, integration, and change of the data And a data preprocessing step of performing a preliminary data sorting process, a data sorting step, a data sorting step, and a predicting step.

The method according to claim 1,
Wherein the data mining engine comprises:
The algorithm includes algorithms such as time series, artificial neural network, decision tree, rule, linear regression analysis, etc., and combines each of the above algorithms through a bagging, boosting, and boat technique to generate a prediction model for an optimal prediction result, And updating the predictive model by repeating the latest data set learning at a predetermined cycle.

The method according to claim 1,
The sales forecast information providing unit,
The sales forecast value is presented and visualized in various sections and forms in the form of a table, a graph, a numerical value, etc. through an interface such as a program, a web, and an application. .

The method according to claim 1,
Wherein the attribute data manual input unit comprises:
Wherein the manager directly inputs the factors affecting sales such as feedback, events, promotions, peripheral events, uniqueness, etc., of the sales forecast value through the interface to improve the data set and the prediction model Automated sales forecasting based on data crawling and manager input.